JP2022511343A - A robot system with a dynamic motion adjustment mechanism and a method for operating it - Google Patents

Abstract

Systems and methods of operating a robotic system to dynamically adjust a planned trajectory or its planned execution are disclosed. The robot system may derive updated waypoints to replace the planned waypoints in the planned orbit for performing the task. Using the updated waypoints, the robot system may perform tasks differently from those initially planned, according to the planned trajectory. [Selection diagram] FIG. 6

Description

Cross-reference to related applications This application claims the benefit of US Provisional Patent Application No. 62 / 957,282 filed January 5, 2020, which is incorporated herein by reference in its entirety.

The technology generally targets robotic systems, and more specifically to systems, processes, and technologies that dynamically adjust upcoming robotic actions (s).

Due to their increased performance and lower costs, many robots (eg machines configured to perform physical actions automatically / autonomously) are now in many areas. Widely used. Robots may be used to perform various tasks (eg, manipulating or transferring objects through space), such as in manufacturing and / or assembly, packing and / or packaging, transportation and / or transportation. be. When performing a task, the robot can replace or reduce the human involvement inherently required to perform the dangerous or repetitive task by reproducing the human action.

However, despite technological advances, robots lack the sophistication needed to recreate the human sensitivities and / or adaptability needed to perform more complex and esoteric tasks. There are many. For example, the robot dynamically (eg, during an ongoing action / task execution) the next action scheduled for the robot, such as in response to a real-world situation and / or a dynamic change to it. ) Often lacks control granularity and flexibility to regulate. Therefore, regardless of various real-world factors, there remains a need for improved technologies and systems that control and manage various aspects of the robot to complete the task.

It is an example of the environment of the embodiment in which a robot system having a dynamic motion adjustment mechanism can operate. It is a block diagram illustrating the robot system which concerns on one or more embodiments of this technique. It is an example of a robot system according to one or more embodiments of the present technology. It is a top view of the robot system which executes the task of an Example which concerns on one or more embodiments of this technique. It is an example of a response profile according to one or more embodiments of the present technology. It is an example of exemplary regulation according to one or more embodiments of the present art. It is a flowchart of the method of the embodiment which operates the robot system of FIG. 1 which concerns on one or more embodiments of this technique. It is an example of the adjustment mechanism of the Example which concerns on one or more embodiments of this technique. It is an example of the adjustment mechanism of the Example which concerns on one or more embodiments of this technique. It is an example of the adjustment mechanism of the Example which concerns on one or more embodiments of this technique. It is an example of the adjustment mechanism of the Example which concerns on one or more embodiments of this technique.

Systems and methods for robotic systems with dynamic motion adjustment mechanisms are described herein. A robotic system configured according to some embodiments (eg, an integrated system of devices performing one or more specified tasks) will take the next robotic action according to a real-world situation or dynamic changes to it. It results in reduced resource consumption, reduced task completion duration, increased efficiency, reduced error rates, etc., based on dynamic adjustments.

Some traditional systems use an offline packing simulator to predetermine the packing order / arrangement. Traditional packing simulators process object information (eg, container shape / size) for a predetermined or inferred set of containers to generate a packing plan. Once determined, the packing plan will include a specific placement position / orientation of the object at the destination (eg, pallets, bins, cages, boxes, etc.), a predefined order of placement, and / or a predetermined movement plan. Direct and / or need them. From a predetermined packing plan, the packing simulator may derive the original requirements (eg, order and / or placement with respect to the object) that match the packing plan or enable the packing plan.

When the packing plan is deployed offline, the plan is independent of the actual packing operation / situation, the arrival of objects, and / or the execution of other systems. Therefore, the overall operation / execution requires that the packages received (eg, at the start / pick-up position) follow a fixed order that matches a predetermined packing plan. As such, the system will receive real-time conditions and / or deviations in the packages received (eg, different orders, positions, and / or orientations), unexpected errors (eg, collisions, lost parts, and / or completely different packages). Inability to meet other real-time factors during real-time packaging requirements (eg, receiving order), and / or execution of packing plans deployed offline.

In contrast to traditional systems, the robotic systems described herein can dynamically adjust packing plans, corresponding motion plans, and / or their execution according to real-time factors. As an exemplary embodiment, a robotic system can use a robotic unit (eg, a transfer unit such as a robotic arm) to perform a planned trajectory (eg, motion planning). The planned trajectory may include planned waypoints that define the targeted position during the movement of the object.

The robot system may track progress along a planned trajectory, taking the next robotic action (eg, speed, setting, state, etc.) corresponding to one or more rest of the planned trajectory. It may be adjusted dynamically. To update, the robot system may derive a new set of updated waypoints to replace the planned waypoints. The updated waypoint may be on or along the planned trajectory, stopping, resuming, and relocating the robot and the target object held / carried by the robot. It may accommodate dynamic adjustments to the execution of tasks such as / or undoing and / or adjusting the rate of movement relative to the robot and the target object.

In some embodiments, the robot system responds to input / output conditions such as received commands, error detection, and / or other changes in the context or environment associated with the planned / executed trajectory. And the feasibility area along the planned trajectory may be derived. The robot system may derive a feasibility area according to the response profile (eg, capability and / or delay) of the corresponding robot (eg, a robot that performs / follows a planned trajectory). The robot system may use an existing planned trajectory or derive one or more updated waypoints to replace the planned waypoints. The first updated waypoint may be derived as a position within the viable area according to one or more real-time parameters. Alternatively or additionally, the robot system may iteratively update the feasibility area and one or more real-time parameters to reach the targeted endpoint state. Thus, the robot system dynamically performs one or more modes of operating the robot to perform one or more rests of the planned trajectory / to follow one or more rests of the planned trajectory. Can be adjusted.

The following description provides a number of specific details to provide a complete understanding of the technology to be disclosed in due course. In other embodiments, the techniques introduced herein may be implemented without their specific details. In other examples, known features such as specific functions or routines are not described in detail to avoid unnecessarily obscuring the present disclosure. References in this description to "an embodied", "one embodied", or the like are described in the present disclosure as specific features, structures, materials, or properties described. It means that it is included in at least one embodiment. Therefore, the appearance of such a phrase in this specification does not necessarily refer to the same embodiment. On the other hand, such references do not necessarily exclude one from each other. In addition, specific features, structures, materials, or properties may be combined in any suitable manner in one or more embodiments. It will be appreciated that the various embodiments shown in the drawings are merely exemplary representations and are not necessarily drawn to the same scale.

Some details that describe the structure or process that are known and often associated with robotic systems and subsystems, but may unnecessarily obscure some important aspects of the disclosed technology. , Not shown in the following description for the purpose of clarification. Moreover, the following disclosures show some embodiments of different aspects of the technique, but some other embodiments have different configurations or different components than those described in this chapter. You may. Accordingly, the disclosed technique may have other embodiments with additional elements, or other embodiments that do not have some of the elements described below.

Many embodiments or embodiments of the present disclosure described below may take the form of computer-executable or processor-executable instructions, including routines executed by a programmable computer or processor. Those skilled in the art will recognize that the disclosed techniques may be implemented on computer or processor systems other than those shown and described below. The techniques described herein are embodied in special purpose computers or data processors specifically programmed, configured, or constructed to execute one or more of the computer executable instructions described below. May be done. Accordingly, the terms "computer" and "processor" as used herein as a whole refer to any data processor, such as Internet appliances and handheld devices (palmtop computers, wearable computers, cellular or mobile phones, multi). It may include processor systems, processor-based home appliances or programmable home appliances, network computers, and mini-computers, etc.). The information processed by those computers and processors may be presented on any suitable display medium, including a liquid crystal display (LCD). Instructions for performing a computer-executable task or processor-executable task are in any suitable computer-readable medium, including hardware, firmware, or a combination of hardware and firmware, or any suitable computer-readable medium. It may be stored above. The instructions may be contained, for example, in any suitable memory device including a flash drive and / or other suitable medium.

Derivatives thereof, along with the terms "coupled" and "connected", may be used herein to describe the structural relationships between the components. It should be understood that these terms are not intended as synonyms for each other. Rather, in certain embodiments, "connected" may be used to indicate that the two or more elements are in direct contact with each other. Unless otherwise specified in the context, the term "combined" means that two or more elements are either in direct or indirect contact with each other (due to other intermediary elements between them). Even if the above elements are used to indicate that they are cooperating or interacting with each other (for example, for signal transmission / reception, or for function call, etc., which have a cause-effect relationship), or both. good.

<Appropriate environment>
FIG. 1 shows an example of an environment in which a robot system 100 having a dynamic motion adjusting mechanism can operate. The robot system 100 may include one or more units (eg, robots) configured to perform one or more tasks and / or may communicate with one or more units. Aspects of the dynamic motion control mechanism may be implemented or implemented by various units.

For the embodiment shown in FIG. 1, the robot system 100 may include a loading / unloading unit 102, a transfer unit 104 (eg, a pallet loading robot and / or a component picker robot), a transport unit 106, and a loading unit in a warehouse or distribution / shipping hub. 108, or combinations thereof, may be included. Each of the units in the robot system 100 may be configured to perform one or more tasks. The tasks are combined in order to perform operations such as loading and unloading objects from a truck or van, storing them in a warehouse, or unloading objects from a storage location and preparing them for shipment. May be good. For another embodiment, the task may include placing an object on a target position (eg, on the top of a pallet and / or inside a bin / cage / box / container). As described below, the robot system derives a plan for placing and / or stacking objects (eg, placement position / orientation, order of moving objects, and / or corresponding motion plans). May be good. Each of the units may be configured to perform a series of actions according to one or more of the derived plans for performing the task (eg, operating one or more components within it). By letting).

In some embodiments, the task moves the target object 112 (eg, one of the packages, boxes, containers, cages, pallets, etc. corresponding to the task to be performed) from the start position 114 to the task position 116, and the like. Manipulation of the target object 112 (eg, moving and / or reorienting) may be included. For example, the loading / unloading unit 102 (eg, a devanning robot) may be configured to transfer the target object 112 from a position in the carrier (eg, a truck) to a position on the conveyor belt. The transfer unit 104 may also be configured to transfer the target object 112 from one position (eg, conveyor belt, pallet, or bin) to another (eg, pallet, bin, etc.). For another embodiment, the transfer unit 104 (eg, pallet loading robot) may be configured to transfer the target object 112 from its original position (eg, pallet, pickup area, and / or conveyor) to the destination pallet. good. Upon completing the operation, the transport unit 106 may transfer the target object 112 from the area associated with the transfer unit 104 to the area associated with the loading unit 108, the loading unit 108 retracting from the transfer unit 104. The target object 112 may be transferred to a position (eg, a position on the shelf) (by moving a pallet carrying the target object 112). Details regarding tasks and related actions are described below.

For illustrative purposes, the robot system 100 is described in a shipping-centric context, where the robot system 100 is for manufacturing, assembly, packaging, healthcare, and / or other types of automation, and the like. It will be understood that it may be configured to perform tasks within / for other purposes. It will also be appreciated that the robot system 100 may include other units not shown in FIG. 1, such as manipulators, service robots, modular robots, and the like. For example, in some embodiments, the robot system 100 is a pallet unloading unit for transferring objects from a cage cart or pallet on a conveyor, or another pallet, to transfer an object from one container to another. Container switching units, packaging units for covering objects, classification units for grouping objects according to one or more of their properties, manipulating objects differently according to one or more of their properties (eg, classification). It may include a component picking unit for, grouping, and / or transporting), or a combination thereof.

The robot system 100 may include, or may be coupled to, physical or structural members connected at the joints for motion (eg, rotational and / or translational displacement). Structural members and indirect end effectors (eg, gripping, rotating, welding, etc.) configured to perform one or more tasks (eg, grabbing, rotating, welding, etc.) depending on the use / operation of the robot system 100. A kinetic chain configured to manipulate the gripper) may be formed. The robot system 100 is a drive device (eg, a motor, an actuator, a wire) configured to drive or operate (eg, displace and / or reorient) a structural member around or in the corresponding indirect. , Artificial muscles, electroactive polymers, etc.). In some embodiments, the robot system 100 may include a transfer motor configured to transfer the corresponding unit / chassis from location to location.

The robot system 100 may include sensors configured to acquire information used to operate structural members and / or perform tasks such as transporting robotic units. The sensor captures one or more physical characteristics of the robot system 100 (eg, one or more of their structural members / indirect states, situations, and / or positions) and / or one or more physical characteristics of the surrounding environment. It may include devices configured to detect or measure. Some embodiments of the sensor may include accelerometers, gyroscopes, force sensors, strain gauges, tactile sensors, torque sensors, position encoders and the like.

In some embodiments, for example, the sensor is one or more imaging devices configured to detect the surrounding environment (eg, a visual camera and / or an infrared camera, a 2D and / or 3D imaging camera, a rider or a radar. Such as ranging devices) may be included. The imaging device can be processed via machine / computer vision to represent the detected environment, such as digital images and / or point clouds (eg, for automated inspection, robot guidance, or other robotic applications). May be generated. As described in more detail below, the robot system 100 has a target object 112, a start position 114, a task position 116, a posture of the target object 112, a reliability measurement of the start position 114 and / or a posture thereof, or a combination thereof. Digital images and / or point clouds may be processed to identify.

To operate the target object 112, the robot system 100 captures an image of a designated area (eg, a pickup position, such as inside a truck or on a conveyor belt) to identify the target object 112 and their starting position 114. And may be analyzed. Similarly, the robot system 100 identifies another designated area (eg, a unloading position for placing an object on a conveyor, a position for placing an object inside a container, or stacking) to identify a task position 116. Images of (position on the palette for the purpose) may be captured and analyzed. For example, the imaging device may be one or more cameras configured to produce an image of the pickup area and / or one or more cameras configured to generate an image of a task area (eg, a unloading area). May include. Based on the captured images, the robot system 100 may include a start position 114, a task position 116, associated postures, packing / placement planning, transfer / packing order, and / or other processing, as described below. The result may be determined.

In some embodiments, for example, the sensor is a position sensor configured to detect a structural member of the robot system 100 (eg, a robotic arm and / or an endpoint) and / or a corresponding indirect position (eg,). , Position encoder, potentiometer, etc.). The robot system 100 may use position sensors to track structural members and / or indirect positions and / or orientations during task execution.

<Appropriate system>
FIG. 2 is a block diagram illustrating the robot system 100 according to one or more embodiments of the present technology. In some embodiments, for example, the robot system 100 (eg, in one or more of the units and / or robots described above) is one or more processors 202, one or more storage devices 204, 1. Electronic / electrical devices such as one or more communication devices 206, one or more input / output devices 208, one or more drive devices 212, one or more transfer motors 214, one or more sensors 216, or a combination thereof. It may be included. The various devices may be coupled to each other via a wired and / or wireless connection. For example, the robot system 100 includes a system bus, a peripheral component interconnect (PCI) bus or a PCI-Express bus, a hypertext or industry standard architecture (ISA) bus, a small computer system interface (SCSI) bus, and a universal serial bus (USB). , IIC (I2C) bus, or an Institute of Electrical and Electricals Enginers (IEEE) standard 1394 bus (also referred to as "Firefire"). Also, for example, the robot system 100 may include a bridge, adapter, processor, or other signal-related device to provide a wired connection between the devices. Wireless connections are, for example, cellular communication protocols (eg, 3G, 4G, LTE, 5G, etc.), wireless local area network (LAN) protocols (eg, wireless fidelity (WIFI)), peer-to-peer or device-to-device communication protocols (eg, eg). It may be based on Bluetooth, proximity communication (NFC), etc.), Internet of Things (IoT) protocols (eg, NB-IoT, LTE-M, etc.), and / or other wireless communication protocols.

The processor 202 is a data processor (eg, a central processing unit (CPU), a special purpose computer, and / Alternatively, it may include an onboard server). In some embodiments, the processor 202 is included in a separate controller / stand-alone controller operably coupled to other electronic / electrical devices exemplified in FIG. 2 and / or robotic units exemplified in FIG. It may be. Processor 202 may execute program instructions that control / interlock with other devices, thereby causing the robot system 100 to perform actions, tasks, and / or actions.

The storage device 204 may include a non-temporary computer-readable medium in which program instructions (eg, software) are stored. Some embodiments of storage 204 may include volatile memory (eg, cache and / or random access memory (RAM)) and / or non-volatile memory (eg, flash memory and / or magnetic disk drive). .. Other embodiments of storage device 204 may include portable memory drives and / or cloud storage devices.

In some embodiments, the storage device 204 is also used to store processing results and / or predetermined data / thresholds and provide access to processing results and / or predetermined data / thresholds. May be done. For example, the storage device 204 may store master data 252 including a description of an object (eg, a box, a container, and / or a product) that can be operated by the robot system 100. In one or more embodiments, the master data 252 may include recorded data for each such object. The recorded data are dimensions, shapes (eg, templates for potential poses and / or computer-generated models for recognizing objects in different poses), color schemes for objects that are expected to be manipulated by the robot system 100. , Images, identification information (eg, barcodes, quick response (QR) codes®, logos, etc., and / or their predicted positions), predicted weights, other physical / visual properties, or them. May include a combination of. In some embodiments, the master data 252 is the mass center (CoM) position for each of the objects or their estimation, predicted sensor measurements corresponding to one or more actions / procedures (eg, force, torque, pressure). , And / or for contact measurements), or combinations thereof, and may include operation-related information about the object.

Communication device 206 may include circuits configured to communicate with external or remote devices over a network. For example, the communication device 206 may include a receiver, a transmitter, a modulator / demodulator (modem), a signal detector, a signal encoder / decoder, a connector port, a network card, and the like. The communication device 206 may be configured to transmit, receive, and / or process electrical signals according to one or more communication protocols (eg, Internet Protocol (IP), wireless communication protocol, and the like). In some embodiments, the robot system 100 exchanges information between units of the robot system 100 and / or exchanges information with an external system or device of the robot system 100 (eg, reporting, data collection, etc.). Communication device 206 may be used for analysis and / or troubleshooting purposes.

The input / output device 208 may include a user interface device configured to communicate and / or receive information from a human operator. For example, the input / output device 208 may include a display 210 and other output devices for communicating information to a human operator, such as a speaker, a tactile circuit, or a tactile feedback device. The input / output device 208 may also include control or reception devices such as keyboards, mice, touch screens, microphones, user interface (UI) sensors (eg, cameras for receiving motion commands), wearable input devices, and the like. In some embodiments, the robot system 100 may use input / output devices 208 to interact with human operators in performing actions, tasks, actions, or combinations thereof.

The robot system 100 may include physical or structural members indirectly connected to movement (eg, rotational and / or translational displacement). Structural members and indirect end effectors (eg, gripping, rotating, welding, etc.) configured to perform one or more tasks (eg, grabbing, rotating, welding, etc.) depending on the use / movement of the robot system 100. A kinetic chain configured to manipulate the gripper) may be formed. The robot system 100 is a drive device 212 (eg, a motor, an actuator, etc.) configured to drive or operate (eg, displace and / or reorient) a structural member around or in the corresponding indirect. Wires, artificial muscles, electroactive polymers, etc.) may be included. In some embodiments, the robot system 100 may include a transfer motor configured to transfer the corresponding unit / chassis from location to location.

The robot system 100 may include sensors 216 configured to acquire information used to operate structural members and / or perform tasks such as transporting robotic units. Sensor 216 is one or more physical characteristics of the robot system 100 (eg, one or more of their structural members / indirect states, situations, and / or positions) and / or one or more physical characteristics of the surrounding environment. May include devices configured to detect or measure. Some embodiments of the sensor 216 may include accelerometers, gyroscopes, force sensors, strain gauges, tactile sensors, torque sensors, position encoders and the like.

In some embodiments, for example, the sensor 216 is one or more imaging devices 222 configured to detect the surrounding environment (eg, a visual camera and / or an infrared camera, a 2D and / or a 3D imaging camera, a rider). Alternatively, it may include a ranging device such as a radar). The imaging device 222 can be processed via machine / computer vision (eg, for automated inspection, robot guidance, or other robotic applications) of digital images and / or point clouds in a detected environment. Representations may be generated.

To operate the target object 112, the robot system 100 (eg, via the various circuits / devices described above) has designated an area (eg, via the various circuits / devices described above) to identify the target object 112 and their starting position 114. Images of the pickup position, such as inside a truck or on a conveyor belt) may be captured and analyzed. Similarly, the robot system 100 identifies another designated area (eg, a unloading position for placing an object on a conveyor, a position for placing an object inside a container, or stacking) to identify a task position 116. Images of (position on the palette for the purpose) may be captured and analyzed. For example, the imaging device 222 may be one or more cameras configured to generate an image of the pickup area and / or one or more cameras configured to generate an image of a task area (eg, a unloading area). May include. Based on the captured images, the robot system 100 may include a start position 114, a task position 116, associated postures, packing / placement planning, transfer / packing order, and / or other processing, as described below. The result may be determined.

In some embodiments, for example, the sensor 216 is configured to detect structural members of the robot system 100 (eg, robotic arms and / or endpoints) and / or corresponding indirect positions. (For example, position encoder, potentiometer, etc.) may be included. The robot system 100 may use position sensors 224 to track structural members and / or indirect positions and / or orientations during task execution. The robot system 100 tracks the detected position from the sensor 216 in order to derive tracking data 254 representing a set of current and / or past positions with respect to the target object 112 and / or the structural member of FIG. The location, tracked orientation, etc. may be used.

<System architecture of the example>
FIG. 3 is an example of the robot system 100 of FIG. 1 according to one or more embodiments of the present technology. The robot system 100 may include a motion planner circuit 302, a bridge circuit 304, and / or a robot 306.

The motion planner circuit 302 (eg, the processor 202 in FIG. 2 and / or the circuit corresponding to the separate device / accommodation) is to derive the planned trajectory 322 for operating the robot 306 to perform the corresponding task. It may be configured in. For example, each planned orbit 322 operates or moves the corresponding target object 112 of FIG. 1 from the start position 114 of FIG. 1 to the task position 116 of FIG. 1 robot 306 (eg, transfer of FIG. 1). It may be for operating the unit 104). In some embodiments, the motion planner circuit 302 may acquire and process data from the imaging device 222 of FIG. 2 to identify and identify the target object 112 and the task position 116. The motion planner circuit 302 may derive a planned trajectory 322 based on iteratively deriving a path segment for a target object 112 from task position 116 to start position 114. The motion planner circuit 302 may derive a path segment and a corresponding planned trajectory 322 according to predetermined rules and / or processing. The planned orbit 322 is a set, velocity of a path or segment that follows the target object 112 and / or one or more robotic components (eg, end effectors and / or robotic arms) to accomplish the corresponding task. , A set of procedures, or a combination thereof. The motion planner circuit 302 may communicate the track 322 planned for the bridge circuit 304. For example, the motion planner circuit 302 may transmit to the bridge circuit 304 a command trajectory representing a movement that will be performed by the robot 306 to accomplish the corresponding task.

The bridge circuit 304 (eg, one or more of the processors 202) may be configured to interact with the robot 306 in performing the planned orbit 322. In some embodiments, the bridge circuit 304 controls and performs actions, each comprising a linked set of separate tasks, performed by a set of robots / across a set of robots (eg, a plurality of robots (eg,). , Robots in warehouses or shipping hubs) may be performed as robot system controllers to coordinate / control actions. Therefore, the bridge circuit 304 may control the timing with respect to the robot 306 to perform various parts / embodiments of the planned trajectory 322.

Robot 306 is configured to perform a planned trajectory 322 and perform a corresponding task according to commands and / or settings from the bridge circuit 304 (eg, representation of the planned track 322 or parts thereof). You may. For example, the robot 306 controls the drive device 212 and / or the transfer motor 214 of FIG. 2 so that the robotic arm and / or the end effector steers the target object 112 to grab, transfer, and / or release. It may be operated. As an exemplary embodiment, the robot 306 may follow a planned trajectory 322 or move the robotic arm to place the end effector in a gripping position around the target object 112 at the starting position 114. After grabbing the target object 112 through the end effector at the grab position, the robot 306 may transfer the target object 112 according to a set of paths, velocities, procedures, etc. corresponding to the planned trajectory 322.

In executing the planned orbit 322, the bridge circuit 304 and the robot 306 may iteratively communicate with each other to accomplish the task. For example, the bridge circuit 304 may be an initial position 342 of the robot 306 (eg, a real-time position (s) of a robotic arm, an end effector, some of them, or a combination thereof), and / or a transferred target object 112. The initial position 342 of may be determined. The bridge circuit 304 may determine an initial position 342 prior to execution of the planned orbit 322 based on outgoing communications (eg, commands, settings, etc.) and / or feedback data 362 from the robot 306. As an exemplary embodiment, the bridge circuit 304 may derive an initial position 342 using a deadlocking mechanism and according to previously executed / executed commands, settings, motion plans, and the like. In addition or instead, the bridge circuit 304 may determine the initial position 342 based on the robot's tracked / reported position contained in the feedback data 362. Similarly, the bridge circuit 304 may determine and track the real-time position of the robot 306, a portion thereof, and / or the target object 112 during the planned orbital 322 execution.

The bridge circuit 304 may also track one or more input / output (I / O) states 344 to perform the planned orbit 322. The I / O state 344 may represent the operating state and / or the corresponding progress / state of the robot 306 associated with performing the planned orbit 322. For example, the I / O state 344 may include a suspended state, a restarted state, and / or a canceled state in executing the planned orbital 322. The I / O state 344 may also include a speed change state for adjusting the speed or rate of movement initially associated with the planned orbit 322. The speed change state may include speed changes, updated speed deviations, and / or command / setting communication associated with transitions between speed settings. Details regarding speed changes are described below.

The bridge circuit 304 may further track the error condition 346 associated with the planned execution of orbit 322. For example, the bridge circuit 304 may track the error state 346 based on feedback data 362 that reports the detected error (eg, component loss state) of the robot. The bridge circuit 304 is also based on comparing the reported data (eg, feedback data 362) with the predicted state / progress and / or their updates (eg, velocity changes) of the planned trajectory 322. The error state 346 may be determined.

The bridge circuit 304 may include a track regulator 305. The orbital regulator 305 may include one or more circuits and / or functions configured to regulate the planned orbital 322 and / or their execution. The orbit regulator 305 is planned for I / O state 344, error state 346, grip strength or state, package identification or state, real-time situation, and / or at one or more points along the planned orbit 322. Other real-time parameters may be tracked during the execution of the orbit 322. The orbital regulator 305 may dynamically adjust the planned orbital 322 when the tracked information deviates from the operating state and / or meets the adjustment conditions. In some embodiments, the orbital regulator 305 may use a planned orbital 322, thereby maintaining a planned path of movement and coordinating the execution of the planned orbital 322. One or more waypoints there may be dynamically updated / replaced. Details regarding dynamic regulation are given below.

<Task execution example>
FIG. 4 is a top view of a robot system 100 that executes a task of an embodiment according to one or more embodiments of the present technology. The task of the illustrated embodiment may include transferring the target object 112 from the start position 114 to the task position 116. As described above, the motion planner circuit 302 of FIG. 3 may derive a planned trajectory 322 for performing a task.

In some embodiments, the planned orbit 322 may include one or more planned waypoints 402. The planned waypoint 402 may include a targeted position along the planned trajectory 322 according to one or more system or robotic motion parameters. For example, the planned waypoint 402 is a target for a tracked member (eg, one or more parts of the robot 306, such as an end effector, and / or a target object 112) corresponding to each processing period 404 (T). It may represent the position where. In other words, the bridge circuit 304 and / or robot 306 of FIG. 3 may iteratively move the tracked member to the next planned waypoint during each processing period. In one or more embodiments, the movement of the tracked member may be linear and / or at a constant speed between the planned pairs of waypoints 402. The planned waypoint 402 may represent a position for changing the movement of the tracked member, such as by changing the direction or speed of movement, or by rotating the tracked member.

As an exemplary embodiment, the robot system 100 (eg, via a bridge circuit 304) may track the current position 406 of the tracked member. The robot system 100 may track the current position 406 during the execution of the task and / or while the robot 306 transfers the target object 112 between the execution of the task and the corresponding planned trajectory. Therefore, the bridge circuit 304 can know the current position 406 of the end effector when the planned trajectory 322 for the new task is received. The bridge circuit 304 may set the current position 406 as the initial position 342 in FIG. Therefore, the bridge circuit 304 may send data and / or commands to perform the planned orbit 322 to the robot 306. For example, the bridge circuit 304 may send data and / or commands to the robot 306 to iteratively move the tracked portion to the next one of the waypoints 402 planned over each processing period 404. good.

During the execution of the planned orbit 322, the robot system 100 may monitor the real-time situation. Some embodiments of real-time situations include component loss (eg, dropping the target object 112), inadequate gripping against the target object 112, robot 306 and / or an object separate from the target object 112. / Unexpected contact with structure / Unplanned contact (eg, collision event), predetermined cancellation conditions, mismatched sensor values, unpredictable situations at start / end positions, and behavioral and / or behavior in robot 306. It may include an error situation indicating a mechanical failure or the like. Other embodiments of real-time situations include suspend, resume, cancel commands, and / or suspend commands from external sources (eg, motion planner circuit 302 in FIG. 3) and / or internal sources (eg, orbit regulator 305 in FIG. 3). / Or may include commands provided by other devices / systems, such as speed control commands. The bridge circuit 304 may detect and set the I / O state 344 and / or the error state 346 of FIG. 3 based on monitoring the real-time situation.

During each processing period 404, the bridge circuit 304 and / or the robot 306 may check the I / O state 344. When the I / O state 344 indicates continuous execution of the planned orbit 322 (eg, no restart state and / or interruption / cancellation / speed change), the bridge circuit 304 and / or robot 306 plans. It may act to advance the tracked portion (eg, the end effector and / or the target object 112) to one of the following waypoints 402. The bridge circuit 304 and / or the robot 306 may continue to check for error conditions while advancing the portion tracked to the next waypoint. When an error situation is detected and an error condition 346 is set / detected, the bridge circuit 304 may disable, cancel, adjust, and / or execute the planned orbital 322 execution. You may restart. The bridge circuit 304 (eg, via the orbital regulator 305) may adjust the travel speed and / or waypoint when disabling and canceling the planned orbital 322. Thus, the bridge circuit 304 makes changes to the planned trajectory 322 in a smooth / seamless manner to reduce sudden movements / collisions leading to other failures and / or according to the hardware / physical capabilities of the robot 306. You may do it.

FIG. 5A is an example of a response profile 502 according to one or more embodiments of the present technology. The response profile 502 may represent a physical reaction or execution in the robot 306 when executing a command. For the embodiment illustrated in FIG. 5A, the response profile 502 may represent the speed of the end effector in response to a stop command or suspended state. The vertical axis may represent the speed of the end effector and the horizontal axis may represent time. The response profile 502 may represent a trigger event 504 such as a stop command / interruption state received by the robot 306 and the corresponding response of the robot 306. The robot 306 may respond to the trigger event 504 or execute a completion event, such as by stopping the movement of the end effector. The robot 306 may require a robot processing delay 508 to receive and process the trigger event 504. Following the trigger event 504 and / or processing thereof, the robot 306 may make physical changes, such as by slowing the movement of the end effector to achieve the completion event 506.

The robot system 100 (eg, the bridge circuit 304) may use the response profile 502 to coordinate the execution of the planned trajectory 322. In other words, the robot system 100 can explain the physical or performance characteristics of the robot 306 in coordinating the execution of the planned trajectory 322. In some embodiments, the robot system 100 may use the response profile 502 to derive an updated waypoint that replaces the planned waypoint 402.

FIG. 5B is an example of regulation 520 of an embodiment according to one or more embodiments of the present art. As illustrated in FIG. 5, the robot system 100 of FIG. 1 (eg, via the bridge circuit 304 of FIG. 3 and / or the robot 306 of FIG. 3) places the target object 112 from the start position 114 to the task position 116. The planned orbit 322 of the figure for transfer may be performed. During execution, the robot system 100 may track the current position 406 of the target portion (eg, the end effector and / or the target object 112 in FIG. 1).

When the robot system 100 determines a state change in the I / O state 344 of FIG. 3 and / or the error state 346 of FIG. 3, the robot system 100 has one or more of the planned waypoints 402. Active waypoints 522 (eg, first upcoming point 522a and / or second upcoming point 522b) may be determined. The active waypoint 522 may include an instance of the upcoming planned waypoint 402 beyond the current position 406 or relative to the current position 406 and may include a target portion (eg, a way behind the current position 406). Instances of planned waypoints 402 that have passed through points) or have been traversed by target portions may be eliminated. In some embodiments, the robot system 100 attaches the robot 306 to a representative portion thereof (eg, an end effector) along a planned segment 524 extending between adjacent waypoints of the planned waypoints 402. ) And / or the target object 112 may be operated to move iteratively.

Further, in response to the determined state change, the robot system 100 may access and / or analyze the response profile 502 of FIG. 5 corresponding to the state change. For example, the robot system 100 (eg, the bridge circuit 304) may determine the ability of the robot 306 to perform and complete actions corresponding to state changes. Accordingly, the robot system 100 may derive a viability region 530 representing a position along a planned trajectory 322 capable of completing an adjustment action (eg, an action taken in response to a state change). .. The viability region 530 is the closest / earliest position along the planned trajectory 322 where the adjustment action can be completed (eg, the adjustment can be initiated or the effect can be achieved first). And / or may represent the farthest / slowest position.

The robot system 100 (eg, orbital regulator 305 in FIG. 3) may derive one or more updated waypoints 532 based on the feasibility region 530. The updated waypoint 532 may be along the planned orbit 322. The updated waypoint 532 may be to replace the planned waypoint 402. One or more of the updated waypoints 532 may match the corresponding one or more of the planned waypoints 402. In some embodiments, the robot system 100 attaches the robot 306 to a representative portion thereof (eg, an end effector) along an updated segment 534 extending between adjacent waypoints of the updated waypoints 532. ) And / or the target object 112 may be operated to move iteratively.

The robot system 100 may derive one or more of the updated waypoints 532 within the feasibility area 530. The robot system 100 performs an adjustment action at the current position 406 so that the tracked portion can complete the adjustment action at the next updated waypoint (eg, a waypoint within the viability region 530). You may start. As an exemplary embodiment, the robot system 100 may stop the end effector and / or the transported target object 112 at the next updated waypoint. The robot system 100 may also achieve the speed targeted by the next updated waypoint (eg, increase or decrease in travel speed compared to the planned speed). The robot system 100 may use a plurality of updated waypoints 532 to achieve the desired end point state, such as by iteratively increasing or decreasing the movement speed. When deriving the updated waypoint 532, the robot system 100 can take into account the updated travel speed. The processing period 404 of FIG. 4 may remain constant and the updated waypoint 532 may correspond to the updated travel speed for a constant processing period 404. For example, the distance / distance between the updated waypoints 532 may be reduced compared to the planned waypoint 402 when the updated travel speed is slower.

によって表されてもよく、最大順速度は、

によって表されてもよい。代表的な部分の位置は、ｑと表わされてもよく、対応する速度（例えば、位置の第１の派生）は、

によって表されてもよく、対応する加速度（例えば、位置の第２の派生）は、

によって表されてもよい。現在のセグメント（例えば、現在の位置４０６を含むセグメント）に対する初期位置／ウェイポイントは、

と表されてもよい。 In some embodiments, the response profile 502 comprises (1) the maximum reverse speed of the robot 306 (eg, the largest negative change in the speed of movement between one processing period 404 or the rest thereof) and (2). It may correspond to the maximum forward speed of the robot 306 (eg, the maximum positive change in moving speed between one processing period 404 or the rest of it). The maximum reverse speed is

May be represented by, the maximum forward speed is

May be represented by. The position of the representative portion may be expressed as q and the corresponding velocity (eg, the first derivation of the position) is

May be represented by the corresponding acceleration (eg, a second derivation of position).

May be represented by. The initial position / waypoint for the current segment (eg, the segment containing the current position 406) is

May be expressed as.

、来たるべき計画されたウェイポイント

、及び処理期間４０４（Ｔ）に従って導出されてもよい。例えば、逆境界は、

に基づいて導出されてもよい。前方境界は、最大逆速度

、来たるべき計画されたウェイポイント

、及び処理期間４０４（Ｔ）に従って導出されてもよい。例えば、前方境界は、

に基づいて導出されてもよい。 The viability region 530 may be defined by both (1) reverse boundaries and (2) forward boundaries for upcoming planned waypoints (eg, first upcoming point 522a). Reverse boundary is maximum reverse velocity

, The upcoming planned waypoint

, And may be derived according to the processing period 404 (T). For example, the reverse boundary

It may be derived based on. The front boundary is the maximum reverse speed

, The upcoming planned waypoint

, And may be derived according to the processing period 404 (T). For example, the front boundary

It may be derived based on.

及び最大順速度

によって境界を設けられてもよい。いくつかの実施形態では、目標とされた速度は、処理期間４０４（Ｔ）にわたって次のセグメント（例えば、第１の来たるべきポイント５２２ａ）に対する初期位置と第２の後続のセグメント（例えば、第２の来たるべきポイント５２２ｂ）に対する初期位置との間の差を評価することに基づいて導出されてもよい。したがって、目標とされた速度は、

として表されてもよく、次のセグメントの初期位置は、

と表わされ、第２の後続のセグメントに対する初期位置は、

と表わされる。応答コマンドが実行可能性領域５３０を超えて延長するとき、第１の更新されたウェイポイントは、その境界にあるなど、実行可能性領域５３０内にあるように切り捨てられてもよく、または調節されてもよい。更新されたウェイポイント５３２の１つ目は、１つの処理期間にわたって目標とされた速度及び／または対応する加速度を実行することに基づいて導出されてもよい。 The robot system 100 may derive the first of the updated waypoints 532 that will be located within the feasibility zone 530. In deriving the first updated waypoint, the robot system 100 may determine the targeted speed. The targeted speed is the maximum reverse speed

And maximum forward speed

Boundaries may be provided by. In some embodiments, the targeted speed is the initial position with respect to the next segment (eg, first upcoming point 522a) and the second subsequent segment (eg, first) over the processing period 404 (T). It may be derived based on assessing the difference between the initial position and the upcoming point 522b) of 2. Therefore, the targeted speed is

May be expressed as, the initial position of the next segment is

The initial position for the second subsequent segment is

It is expressed as. When the response command extends beyond the feasibility area 530, the first updated waypoint may be truncated or adjusted to be within the feasibility area 530, such as at its boundaries. You may. The first of the updated waypoints 532 may be derived based on performing a targeted velocity and / or corresponding acceleration over a processing period.

In one or more embodiments, the robot system 100 may calculate one or more intermediate speeds between the current speed / planned speed and the targeted speed. The robot system 100 may calculate the intermediate speed according to the maximum forward / reverse speed or acceleration when the targeted speed is not achievable within one processing period. Therefore, the robot system 100 may iteratively execute an intermediate speed over a plurality of processing periods / waypoints and up to a targeted speed to reach the intermediate speed. The robot system 100 may derive updated waypoints 532 according to intermediate speed / targeted speed and / or corresponding acceleration over each corresponding processing period.

<Example of control flow>
FIG. 6 is a flowchart of the method 600 of the embodiment in which the robot system 100 of FIG. 1 is operated according to one or more embodiments of the present technology. Method 600 may be for dynamically adjusting the planned orbit 322 of FIG. 3 or its execution (after the derivation of that execution and / or during its execution). Method 600 may be performed using the bridge circuit 304 of FIG. 3, the motion planner circuit 302 of FIG. 3, and / or the robot 306 of FIG. Method 600 may be performed on the basis of executing instructions stored in one or more of the storage devices 204 of FIG. 2 by one or more of the processors 202 of FIG. Method 600 may also be performed based on communicating the planned trajectory 322, the adjustment 520 of FIG. 5B, the feedback data 362 of FIG. 3 and / or the corresponding command / setting using the communication device 206. good. The communicated commands / settings may be performed in robot 306, thereby performing tasks corresponding to the planned orbit 322 and / or adjustment 520 for it. In some embodiments, method 600 may be performed using one or more state machines.

At block 602, the robot system 100 may communicate an initially planned trajectory configured to perform a task. For example, the motion planner circuit 302 is a plan for accomplishing a task that requires the operation of the target object 112 of FIG. 1, such as transferring the target object 112 from the start position 114 of FIG. 1 to the task position 116 of FIG. The completed orbital 322 may be derived. In some embodiments, the motion planner circuit 302 is designed by determining the targeted posture with respect to the target object 112 at the task position 116 and iteratively determining the path segment connecting to the starting position 114. The orbital 322 may be derived.

The motion planner circuit 302 may communicate the derived planned track 322 to the bridge circuit 304, and the bridge circuit 304 may receive the initially planned track 322. As described in more detail below, the bridge circuit 304 may control task execution and / or real-time / dynamic coordination for the task.

At block 604, the robot system 100 may identify one or more planned waypoints 402 in FIG. 4 associated with the planned trajectory 322. The planned waypoint 402 may include positions along the planned orbital 322 that are iteratively / incrementally targeted during the set of processing periods 404 of FIG. In other words, the robot system 100 may operate the robot 306 to place a portion (eg, an end effector) and / or a target object 112 that is representative of the planned waypoint 402 at the end of the corresponding processing period 404. good. In some embodiments, identifying the planned waypoint 402 means that the bridge circuit 304 is derived from the received position in the motion planner circuit 302 and contained in the received position. May include accessing the. In another embodiment, identifying the planned waypoint 402 associates the bridge circuit 304 with a processing period 404 (eg, a preset duration between each period) and a planned orbit 322. It may include determining a position along the planned orbit 322 according to a set speed setting (eg, information provided with the planned orbit 322).

At block 606, the robot system 100 may start executing tasks. For example, the robot system 100 initiates task execution based on communication of commands / settings to the robot 306, such as when the bridge circuit 304 initiates a task execution process and initiates a corresponding protocol. May be good. The bridge circuit 304 may further determine an initial position 342 of FIG. 3 of the robot 306, such as its representative portion (eg, an end effector), and / or a predetermined position (eg, a target object 112). The robot 306 may be operated to steer a representative portion (a gripping position identified by a planned trajectory 322 for gripping). When the procedure is complete, the predetermined position may serve as the initial position 342.

In the determination block 608, the robot system 100 may determine whether the task execution has reached the end point according to the planned trajectory 322 (eg, the termination corresponding to the target object 112 located at the task position 116). Status). As described in detail below, the robot system 100 may iteratively transfer the target object 112 along the planned trajectory 322. The robot system 100 may determine whether the execution of the task has reached the end point for each iteration of movement. In some embodiments, the robot system is at the end point when the target object 112 is placed at task position 116 and / or when all commands / settings corresponding to the planned trajectory 322 have been executed / completed. It may be determined that it has been reached. When the task reaches the end point, the robot system 100 may identify the next task as represented in block 610 and the corresponding next planned as indicated by the feedback loop to block 602. The orbit may be communicated.

When the task does not reach the end point, the robot system 100 may identify the next waypoint, as presented at block 612. The robot system 100 (eg, the bridge circuit 304) is based on comparing the current position 406 (eg, the initial position 342 to the first iteration) with the currently maintained / valid set of waypoints. The next waypoint may be identified. The set of maintained / valid waypoints may initially include the planned waypoints 402. The set of maintained / valid waypoints may include the updated waypoints 532 of FIG. 5B after adjustment 520 or in place of the planned waypoints 402 based on adjustment 520. Based on the comparison, the robot system 100 may identify the next waypoint as a waypoint adjacent to (eg, just before) the current position 406 along the direction of travel.

At block 614, the robot system 100 may perform the movement of a representative portion of the robot 306 and / or the target object 112 to the next identified waypoint. For example, the bridge circuit 304 communicates a set of commands and / or settings for operating the robot 306 to make a representative portion of the target object 112 or the robot 306 follow a planned trajectory 322 to the next waypoint. By doing so, the move may be performed. Robot 306 may receive and execute a set of commands and / or settings to move / displace a representative portion of robot 306 and / or target object 112 to the next identified waypoint.

At block 616, the robot system 100 may monitor the real world situation during the execution of the task. For example, the robot system 100 may receive and analyze real-time data from sensor 216 in FIG. 2 to monitor real-world situations. The robot system 100 also includes real-time data from the motion planner circuit 302 (eg, commands and / or other messages), real-time data from the robot unit (eg, feedback data 362 from the robot 306), and / or other. Real-time data from communicable coupled devices / systems (eg, warehouse management systems) may be used for monitoring functions.

In some embodiments, the robot system 100 is the I of FIG. 3 while the representative portion and / or the target object 112 is moving to the next waypoint (eg, during the execution of the corresponding segment movement). The real world situation may be monitored based on monitoring the / O state 344. The I / O state 344 may correspond to the result of analyzing real-time sensor data and / or received communication data, with the robot system 100 (eg, robot 306) completing the task execution and the target object 112. It may represent the ability to operate. The robot system 100 (eg, bridge circuit 304) monitors the I / O state 344 by detecting a suspended state, a restart state, a canceled state, a speed change state, an error state 346, and / or changes to them. May be good.

In decision block 618, the robot system 100 may determine whether the monitored real-world situation meets a trigger for adjusting an ongoing task. The trigger may represent a situation that requires a change to the task, such as a situation corresponding to one or more of the states described above. As an exemplary embodiment, the robot system 100 may detect and illustrate lower grip strength, lost parts, collisions, and / or other unpredictable situations that occur during task execution. can do.

When the monitored real-world situation does not meet the trigger condition, the robot system 100 may continue to perform the task according to the initially planned trajectory 322, as represented by the feedback loop. Therefore, the robot system 100 may perform the processes described above for blocks 608-616, or may identify the next waypoint within the planned orbit 322, as initially planned. The task may be executed iteratively.

When the monitored real-world situation meets the trigger condition, the robot system 100 dynamically derives one or more task adjustments (eg, adjustment 520 in FIG. 5B) as represented by block 620. May be good. In some embodiments, the robot system 100 may dynamically derive the adjustment 520, such as by deriving the updated waypoint 532 of FIG. 5B, based on the I / O state 344. For example, in response to detecting a suspended state, a restart state, a canceled state, a speed change state, and / or an error state, the robot system 100 sets an updated waypoint 532 along the planned trajectory 322. It may be dynamically derived (during task execution, for example, when a representative portion of the robot 306 is between the start position 114 and the task position 116). The updated waypoint 532 may be configured to replace a planned waypoint 402 that includes one or more of the upcoming waypoints / remaining waypoints. The updated waypoints 532 have a processing period of 404 such that each waypoint represents a targeted position that will be reached by the target object 112 or a representative portion at the end of the corresponding processing period 404. May correspond to.

In some embodiments, the robot system 100 dynamically derives task adjustments based on identifying the response profile 502 of FIG. 5A associated with the detected trigger, as shown in block 622. You may. For example, the robot system 100 may identify a response profile 502 for decelerating, accelerating, and / or stopping the movement of a representative portion with respect to the robot 306. The robot system 100 is based on accessing predetermined information / known information about the robot 306 (for example, information stored in the storage device 204 of FIG. 2, such as in the master data 252 of FIG. 2). And / or the response profile 502 may be identified based on communicating the profile with the robot 306. Accordingly, the robot system 100 is capable of performing adjustments or parts thereof (eg, acceleration, deceleration, stop, etc.), such as maximum reverse speed and / or maximum forward speed associated with the corresponding response profile 502. You may identify what represents.

At block 624, the robot system 100 may determine the feasibility region 530 based on the response profile 502. The robot system 100 (eg, via a bridge circuit 304) is a viable area in front of the current position 406 along the planned trajectory 322 and representing a representative portion of the target object 112 and / or the robot 306. 530 may be determined. The robot system 100 is based on mapping the response profile 502 according to the projected timing of the updated commands / settings and the extrapolated position / distance based on the speed / time from the viability region 530. , The feasibility area 530 may be determined. Therefore, the robot system 100 may determine the viability region 530 based on deriving the reverse boundary and / or the forward boundary associated with each of the maximum reverse velocity and / or the maximum forward velocity. Reverse and forward boundaries may be used to define a viable region 530 (eg, the region between the reverse and forward boundaries). The robot system 100 may use the feasibility area 530 to identify / present a position along the planned trajectory 322 on which the adjustment 520 can initially be effective.

At block 626, the robot system 100 may determine a target speed for the detected trigger. For example, the robot system 100 may determine the target speed as a zero movement state or a stopped movement state when the monitored situation corresponds to a predetermined state such as stop, cancellation, and / or retrograde. .. Also, the robot system 100 is associated with a velocity change step and / or a retrograde state (eg, a vector having opposite directions along a planned trajectory 322) / velocity change step and / or a retrograde state (eg, a plan). The target velocity may be determined as the target velocity by a vector having opposite directions along the resulting orbit 322). Further, the robot system 100 may determine the target speed according to one or more predetermined processes and / or equations in response to the detection of the error condition 346.

The target speed may differ from the initially planned orbit 322 or the planned speed associated with those parts to come. In other words, the target velocity may correspond to a dynamically derived adjustment and / or end point state / situation for the planned orbit 322.

In the determination block 628, the robot system 100 (eg, via the bridge circuit 304) may determine whether the change to the target speed can be performed over one processing period. For example, the robot system 100 may compare the target speed and / or the difference between the current speed and the target speed with the maximum speed / boundary speed associated with the response profile 502. When the target speed is not feasible within one processing period (eg, when the target speed exceeds the maximum speed change associated with the robot 306), the robot system 100 has one or more, as represented in block 630. The intermediate speed of may be determined. In other words, the robot system 100 may use a plurality of processing periods to pass an intermediate speed and reach a target speed. In some embodiments, the robot system 100 may determine an intermediate speed as the maximum speed / boundary speed closest to the target speed. In other embodiments, the robot system 100 may determine the minimum number of processing periods / iterations required to reach the target speed. The robot system 100 may calculate the intermediate speed (s) based on dividing the target speed by a determined minimum number. The intermediate speed (s) may include a value / setting between the current speed and the target speed.

At block 632, the robot system 100 may derive updated waypoints based on the derived speed (s) (eg, target speed and / or intermediate speed (s)). In some embodiments, the bridge circuit 304 may be flagged according to the viable determination described above. The bridge circuit 304 may use the determined speed for the first upcoming segment / next upcoming segment to derive the first of the updated waypoints 532. The first waypoint may be derived based on the upcoming speed bounded by the maximum speed / adjustment associated with the response profile 502 as described above. Therefore, the robot system 100 may derive a first waypoint as a position within the feasibility region 530.

As an exemplary embodiment, the robot system 100 determines that the change will be performed at the next upcoming waypoint in front of the current position 406 (eg, the first upcoming waypoint 522a in FIG. 5B). You may. Therefore, the response profile 502 may be mapped to the segment following the first upcoming waypoint 522a. The viability region 530 describes the first upcoming waypoint 522a and the second upcoming waypoint 522b in FIG. 5B, as the response profile 502 describes the changes that can be made within one processing period. May include subsegments between and. The robot system 100 may derive a first updated waypoint as a position within the viable region 530, such as according to the targeted speed and / or the position closest to the targeted speed. For example, if the robot 306 is capable of performing the desired changes within the upcoming processing period, the robot system 100 is based on predicting the execution of the targeted adjustment (eg, maximum acceleration / deceleration). Based on one or more predetermined processes for predicting distance / position), a first updated waypoint may be derived. If the robot 306 requires more processing time than one to perform the change, the robot system 306 is the furthest boundary of the viable region 530, or the division described above for the first upcoming point 522a. The first updated waypoint may be derived as the location.

In some embodiments, the robot system 100 may derive the remaining set of updated waypoints 532 based on the targeted speed and / or intermediate speed (s). In another embodiment, the robot system 100 may derive one upcoming updated waypoint per iteration.

The robot system 100 may use updated waypoints 532 to perform adjustment 520, as represented by the feedback loop. Thus, based on the I / O state 344, the robot system 100 (eg, via the bridge circuit 304) operates the target object 112 according to the updated waypoint 532 instead of the planned waypoint 402. You may perform adjustment 520 for the task for. For the rest of the planned orbit 322, the bridge circuit 304 targets / is to come waypoint 532 instead of the planned waypoint 402 for subsequent processing periods. You may generate commands / settings to operate the robot 306 to follow 532. Therefore, the bridge circuit 304 may operate the robot 306 to transition from the current speed to the target moving speed across one or more updated waypoints and the corresponding processing period (s). For example, when feasible, the bridge circuit 304 may operate the robot 306 to transition from the current speed to the target speed during the initial processing period according to the detected trigger condition / state. Also, if not feasible over one period / iteration, the bridge circuit 304 may operate the robot 306 to transition from the current speed to an intermediate speed during the initial processing period. The bridge circuit 304 may operate the robot 306 to transition from an intermediate speed to a target speed during the subsequent processing period. The bridge circuit 304 may iteratively move the target object 112 and / or the representative portion to perform the task and subsequent adjustments 520 to it. Therefore, the bridge circuit 304 may operate the robot 306 to stop, reverse, and / or adjust the speed for moving the target object 112 and / or the representative portion.

<Detailed example of execution mode>
7A-7D are illustrations of the adjusting mechanism (eg, state machine) of the embodiment according to one or more embodiments of the present art. FIG. 7A illustrates an orbital execution mechanism 702 (eg, one or more of the bridge circuit 304 of FIG. 3, processor 202 of FIG. 2, or a combination thereof). The orbit execution mechanism 702 may be configured to manage the overall flow for coordinating the execution of the planned orbit 322 of FIG. The orbit execution mechanism 702 may correspond to the method 600 of FIG. 6, a part thereof, or an alternative embodiment.

The orbit execution mechanism 702 may be executed according to the processing period 404 of FIG. The orbital execution mechanism 702 may transition through the various states described below during each processing period starting and ending at "X".

During each period or moment, the orbital execution mechanism 702 may check the I / O state 344 of FIG. 3 as represented by the "CheckIO" block. The orbit execution mechanism 702 may check the I / O state 344 or changes to it for block 616 of FIG. 6, as described above. For example, the orbit execution mechanism 702 may detect an occurrence or change in a suspended state, a restarted state, a canceled state, a speed change state, or the like.

After checking the I / O, the orbital execution mechanism 702 may move the robot as represented by the "MoveRobot" block. The orbit execution mechanism 702 is currently maintained, such as the planned orbit 322 of FIG. 3 with the planned waypoint 402 of FIG. 4, or the adjustment 520 of FIG. 5B with the updated waypoint 532 of FIG. 5B. The robot 306 of FIG. 3 may be operated according to the trajectory. For example, the orbit execution mechanism 702 may correspond to the processing described above for the block 614 of FIG.

In some embodiments, the orbital execution mechanism 702 may check for errors (eg, error state 346 in FIG. 3), as represented by the "CheckErrors" block. The orbit execution mechanism 702 may check the error condition 346 for the block 616 as well as described above. In other words, the orbit execution mechanism 702 divides the real-world situation monitoring so that a portion of the situation (eg, I / O state 344) is checked before / during the move and errors are checked after the move. May be good. For example, the orbit execution mechanism 702 may check for errors by evaluating the movement performed. Some embodiments of the evaluated error situation are unexpected / unplanned contact with the target object 112 and / or another object or structure between the represented parts, dropping the target object ("Parts". "Loss") may include one or more predetermined cancellation states (eg, shifting an object at a target position), misalignment of a sensor valve, and the like. The orbit execution mechanism 702 may use predetermined processing to determine the response action corresponding to the detected error. Response actions may include moving backwards, canceling a task, resuming a task, and so on.

The orbital execution mechanism 702 may then determine the next move, as represented by the "PlanNextMove" block. The orbit execution mechanism 702 may plan the next movement for the blocks 612, 618, and 620 of FIG. 6 as similarly described above. For example, the orbital execution mechanism 702 may determine whether the I / O state 344 and / or the error state 346 has been flagged or detected in the steps described above. The next planned move may correspond to continuing an existing plan when no trigger condition is detected. If one or more trigger conditions are detected, the trajectory execution mechanism 702 will cancel the execution of the task, end the execution of the task, and / or slow down the movement. You may decide that it will be.

The orbit execution mechanism 702 may calculate indirect information (eg, details for performing the next movement) according to the planned next movement. If no trigger condition is detected, the orbit execution mechanism 702 derives the next move based on identifying the next waypoint and the corresponding velocity according to the remaining set of waypoints / existing set. May be. If one or more trigger conditions are detected, the orbit execution mechanism 702 may start the orbit regulator 305 of FIG. The trajectory regulator 305 may correspond to block 620 and dynamically derive details for remaining waypoints / task adjustments that deviate from existing waypoints (eg, updated waypoints 532 in FIG. 5B). May be. For example, the orbital regulator 305 may determine a new target speed and / or a corresponding intermediate speed set for the next planned movement. In some embodiments, the trajectory regulator 305 and / or motion planner circuit 302 of FIG. 3 may redistribute the trajectory based on the trigger condition.

FIG. 7B illustrates a command flow 704 (eg, state machine flow) of an embodiment for the orbital execution mechanism 702 of FIG. 7A. Flow 704 may represent various command states and transitions between command states for the bridge circuit 304 of FIG. In other words, the flow 704 may represent a transition between commands / actions and execution states that can be executed by the robot 306 of FIG.

The flow 704 may include a TR streaming state representing communication of data and / or commands to the bridge circuit 304. Based on the TR streaming state, the flow 704 may represent a flow between different orbit types. In some embodiments, the orbital type may include T-command, T-connect, T-cancel, and / or T-reverse connect.

The T-command type may be configured to enter the orbit. For example, the bridge circuit 304 of FIG. 3 may receive the planned orbit 322 of FIG. 3, as illustrated in block 602 of FIG. The T-command type may correspond to the initially planned trajectory 322 of FIG. 3 derived by the trajectory regulator 305 of FIG. The bridge circuit 304 may continue to execute the planned orbit 322 as initially derived for the T-command type.

The flow 704 may transition to a different orbital type or state in response to a real-time situation (eg, I / O state 344 in FIG. 3 and / or error state 346 in FIG. 3). For example, the determination of the suspension status, the restart status, and / or the speed change status can be made to transition from the T-command to the T-connect in the orbit controller 305. The T-connect type orbit may include the adjustment 520 of FIG. 5B. The T-Connect may respond to a deceleration command to zero speed for a suspension situation and an acceleration command to a previous speed or an ongoing speed for a restart situation. The trajectory regulator 305 may calculate an execution plan for accelerating / decelerating a representative portion of the robot 306 in response to a speed change situation. In some embodiments, the execution plan may include a current moving speed multiplier (CTSM) configured to guide the speed change for each iteration up to the target speed. The execution plan may further include an external travel rate multiplier (ETSM) received from another device / system. In some embodiments, the update may be stored as an existing activated / in-progress trajectory, and the flow 704 again transitions from T-connect to T-command for subsequent executions of the updated trajectory. You may.

The T-cancel type may be for canceling the execution of the orbit. The T-cancellation trajectory type may be generated in response to a detected error condition (eg, error condition 346 in FIG. 3) and / or during the detected error condition. The T-cancel trajectory type may correspond to one or more commands for stopping at zero speed. In some embodiments, the T-cancel type may correspond to completing / completing a task. For example, when the robot 306 finishes manipulating the target object 112 (eg, by placing it at task position 116), the T-cancel type is planned to be completed from the processing flow before starting a new task. It may be generated to delete the orbital 322. Therefore, the flow 704 may enter the TR end state when the T-cancel has no error or trigger condition. Instead, for one or more predefined trigger conditions, T-cancellation was problematicly planned before transitioning to the TR stop phase for irreparable error situations (eg, component loss). The orbit 322 may be erased.

The T-reverse connect type trajectory may correspond to one or more predetermined error situations. For example, the T-Reverse Connect responds to the robot 306 colliding with or blocking one or more objects during the transfer movement and / or during the picking / placement operation. May be generated. Further, the T-reverse connect may be generated when the planned position of the robot 306 (for example, the posture of the end effector) does not match the detected position of the robot 306.

FIG. 7C illustrates an execution flow 706 of an embodiment for the orbital execution mechanism 702 of FIG. 7A. Execution flow 706 may represent different states and transitions for each of the orbital types described above (eg, in FIG. 7B). For each command / action, the standard streaming state (Regular Streaming) has been updated in FIG. 5B following the current set of waypoints (eg, waypoint 402 initially planned in FIG. 4 and adjustment 520 in FIG. 5B. The robot system 100 of FIG. 1 (eg, via the bridge circuit 304 of FIG. 3 and the robot 306 of FIG. 3) following the waypoint 532) may be represented.

The robot system 100 can take into account the delay or lag associated with the communication between the bridge circuit 304 and the robot 306, and the corresponding processing time. For example, the bridge circuit 304 and / or the robot 306 may execute a state of waiting for a final position (WaitForFinalPos) and waiting for the robot to perform a commanded action. The final position of the robot 306 may be acquired by the bridge circuit 304 at the end of the action. The robot 306 may transmit the feedback data 362 of FIG. 3 reporting the final position so as to end the standby state. Alternatively or additionally, the bridge circuit 304 may calculate the final position based on the action and / or feedback data 362 (eg, completion status report) instructed to exit the standby state.

In some embodiments, the robot system 100 may include an error recovery mechanism configured to respond to a predetermined error condition. For example, the error recovery mechanism may correspond to automatically reversing the movement as described above (eg, T-reverse connect in FIG. 7B). The robot system 100 may transition from the standard streaming state and / or from the standby state to the error recovery mechanism. The robot system 100 may re-transition from the error recovery state to the standard streaming state and / or the standby state.

The robot system 100 can further take into account the encoder or processing delay in the robot 306. For example, the bridge circuit 304 and / or the robot 306 may execute a state (WaitForEncodeConvrg) waiting for processing delay or convergence in the encoder. The encoder of the robot 306 may stop after the robot 306 reaches the final targeted position at the end of the movement.

Robot 306 may arrive at its final position based on its trajectory to its end point. If the robot system 100 determines an error condition along the trajectory before reaching the end point, the bridge circuit 304 may stop the movement of the robot 306. In response to the error, the bridge circuit 304 may withhold the command associated with the final position. The execution flow 706 may directly transition from the standard streaming state to the convergence standby state.

The robot system 100 may stop the robot 306 and terminate the state machine, the bridge circuit 304 being at or within a predetermined distance from the robot 306 at a designated position. You may wait for the encoder to converge to ensure that it is. When the robot 306 stops, the robot system 100 may use the stop points to recalculate the next trajectory.

FIG. 7D illustrates the orbital flow 708 of the embodiment for the orbital execution mechanism 702 of FIG. 7A. The orbital flow 708 may exemplify the relationship between different orbital transitions. The orbital flow 708 may determine the transition prior to determining the orbital type to what is targeted by the transition. Therefore, the robot system 100 of FIG. 1 may prioritize which events should follow and may result in a hierarchy between different transitions. Different state transitions may be used to make different types of decisions to communicate or select transitions.

The orbital flow 708 may correspond to the state described above with respect to the command flow 704 of FIG. 7B. For example, the TR streaming state in FIG. 7D may correspond to the TR streaming state and the T-command state in FIG. 7B. TR interruption, TR restart, TR cancellation, TR speed change, and TR retrograde may correspond to the transition trigger described in FIG. 7B. The TR end state may correspond to the transition to the TR end state of FIG. 7B (for example, arrival at the final position where there is no error during the operation).

The robot system 100 may use the dynamic adjustment 520 to smoothly and seamlessly describe the real world situation. Due to the relatively large amount of time and resources required to redistribute the trajectory using the motion planner circuit 302 of FIG. 3, the robot system 100 has been updated along the initially planned trajectory 322. A bridge circuit 304 may be used to dynamically derive the waypoint 532. For example, immediately stopping or reversing the movement of the robot 306 in response to a real-world situation may cause the robot 306 to jerk or vibrate, which can lead to further unwanted errors. May increase. Instead, continuous execution of the initially planned trajectory regardless of real-world conditions (eg, errors) can result in additional errors (eg, collisions) and / or resources. It can be wasted (eg, following component loss). In this way, by replacing the planned waypoints 404 with the updated waypoints 532, the robot system 100 can substantially perform dynamic adjustments as well as overall efficiency and error ratios. Increase. Moreover, the robot system 100 described above may perform tasks practically (eg, via the method 600 and / or the state machine of FIG. 6) as well as real-world situations. Adjust in consideration.

<Conclusion>
The embodiments of the disclosed techniques for carrying out the invention are not intended to be comprehensive or to limit the disclosed techniques to the exact form disclosed above. Although specific embodiments for the disclosed techniques have been described above for illustration purposes, various equivalent modifications are possible within the disclosed techniques, as will be appreciated by those of skill in the art. For example, processes or blocks are presented in a given order, but alternative embodiments may execute routines with steps in different orders, or employ systems with blocks. Some processes or blocks may be deleted, moved, added, subdivided, or combined to provide alternative or subordinate combinations. , And / or may be modified. Each of those processes or blocks may be performed in a variety of different ways. Also, although the processes or blocks are indicated at once as being executed in sequence, those processes or blocks may instead be executed or executed in parallel, or at different times. Moreover, any particular number referred to herein is merely an example, and alternative embodiments may employ different values or ranges.

In consideration of the embodiment for carrying out the above invention, those changes and other changes may be made to the disclosed technology. The embodiments for carrying out the invention have described the best modes considered with specific embodiments of the disclosed technology, but the disclosed technology is in many ways, no matter how detailed the above description appears in the text. It may be carried out in. The description of the system may vary significantly in that particular embodiment, and yet. It is still included by the techniques disclosed herein. As mentioned above, the particular term used in describing a particular feature or aspect of the disclosed technology is limited to any particular property, feature, or aspect with which the term is associated. It should not be taken to imply that it is redefined as. Therefore, the invention is not limited except as provided in the appended claims. In general, the terms used in the following claims are the techniques disclosed in the particular embodiments disclosed herein, unless the chapter of embodiments for carrying out the invention explicitly defines such terms. Should not be construed as limiting.

A particular aspect of the invention is presented below in the form of a particular claim, but the applicant will consider various aspects of the invention in the form of any number of claims. Therefore, the applicant reserves the right to pursue additional claims after the application of this application so as to pursue such additional claims in either this application or the continuation application.

Claims (20)

It ’s a way to operate a robot system.
Receiving a planned trajectory for manipulating the target object,
Identifying a set of planned waypoints along the planned trajectory, where each waypoint in the set of planned waypoints places a representative portion of the target object or robot. Representing the increasingly targeted position on the planned orbit to do so
Performing a task according to the planned trajectory by communicating a set of commands or settings for operating the robot so that the target object or the representative portion of the robot follows the planned trajectory. To get started and
Repetitively performing the task of transferring the target object or the representative portion of the robot to a subsequent planned waypoint on the planned orbit.
Monitoring input / output (I / O) conditions that represent the ability to complete the task execution and manipulation of the target object during the iterative execution of the planned trajectory.
Dynamically deriving an updated set of waypoints along the planned trajectory that replaces the planned set of waypoints based on the I / O state.
The said for transferring the target object or the representative portion of the robot according to the updated set of waypoints, rather than following the planned set of waypoints based on the I / O state. Performing adjustments to the task and
A method. Monitoring the I / O state represents a real-time real-world situation associated with the ability of the robot system to complete the task, a suspended state, a restart state, a canceled state, a speed change state, and / or an error. The state includes detecting during the execution of the task.
Dynamically deriving the updated set of waypoints and performing the adjustments to the task iteratively can be the suspended state, the restarted state, the canceled state, the speed change state, and /. Or, it is executed in response to the detection of the error state.
The method according to claim 1. Dynamically deriving the updated set of waypoints involves determining a target travel speed that is different from the planned travel speed associated with the planned set of waypoints.
Performing the adjustment for the task comprises transitioning to the target movement speed across one or more waypoints in the updated set of waypoints.
The method according to claim 1. The updated set of waypoints and the planned waypoint set correspond to a processing period, and each waypoint in the updated waypoint set and the planned waypoint set is Represents a targeted position that the target object or the representative portion of the robot will reach at the end of the processing period.
Dynamically deriving the updated set of waypoints involves determining an intermediate speed between the current speed and the target speed.
Performing the adjustment for the task
Transitioning to the intermediate movement speed during the initial processing period and
The transition to the target movement speed during the subsequent processing period following the initial processing period, and
Including repetitive transitions to the target movement speed by
The method according to claim 3. The method of claim 3, wherein performing the adjustment to the task comprises transitioning to the target movement speed for stopping the movement of the target object and / or the representative portion of the robot. .. The method of claim 3, wherein performing the adjustment to the task involves transitioning to the target movement speed for reversing the movement of the target object and / or the representative portion of the robot. .. Dynamically deriving the updated set of waypoints is an execution along the planned trajectory and in front of the current position representing the target object and / or the representative portion of the robot. Including determining the potential area
The method of claim 1, wherein the viable region is a position along the planned orbit and is intended to represent a position where the adjustment is first effective. 7. The method of claim 7, wherein the feasible area is determined according to a response profile that represents the physical ability of the robot to perform the adjustments to the task or a portion thereof. The feasibility area is determined based on mapping the response profile from the current location.
The updated set of waypoints comprises a first waypoint located within the feasibility zone.
The method according to claim 8. The viable region is defined by (1) the maximum negative change in speed during the treatment period and (2) the maximum positive change in speed during the treatment period.
The first waypoint is derived based on the difference between the second coming position and the first coming position evaluated over the processing period.
The method according to claim 9. It ’s a robot system,
With communication devices
With at least one processor coupled to the communication device,
The communication device is
Receiving a planned trajectory from the motion planner circuit to perform the task of transporting the target object from the start position to the task position, and
Communicating commands, settings, and / or feedback data with the robot to perform the planned trajectory.
Is configured to do
The at least one processor
Identifying a set of planned waypoints along the planned trajectory, where each waypoint in the set of planned waypoints places a representative portion of the target object or robot. Representing the increasingly targeted position on the planned orbit to do so
Initiating the execution of the task according to the planned trajectory, based on an initial set of commands and / or settings communicated to the robot.
Repetitively performing the task of transferring the target object or the representative portion of the robot to a subsequent planned waypoint on the planned orbit.
Monitoring input / output (I / O) conditions that represent the ability to complete the task execution and manipulation of the target object during the iterative execution of the planned trajectory.
Dynamically deriving an updated set of waypoints along the planned trajectory that replaces the planned set of waypoints based on the I / O state.
The said for transferring the target object or the representative portion of the robot according to the updated set of waypoints, rather than following the planned set of waypoints based on the I / O state. Performing adjustments to the task and
And
The adjustment for the task corresponds to a subsequent set of commands and / or settings communicated to the robot, the robot system. With the motion planner circuit configured to derive the planned trajectory,
With the robot configured to perform the task according to the planned trajectory and / or the adjustment to the task.
Further prepare
The communication device and the at least one processor are communicably coupled between the planner circuit and the robot, and a bridge circuit configured to control the robot to perform the task. include,
The robot system according to claim 11. The at least one processor
Identifying the planned set of waypoints, initiating the execution of the task, performing the task iteratively, monitoring the I / O status, the updated set of waypoints. One or more state machines configured to control the execution of the task, based on dynamically deriving and / or performing the adjustment to the task.
11. The robot system according to claim 11. The monitored I / O state represents a real-time real-world situation associated with said ability of the robot system to complete the task, a suspended state, a restart state, a canceled state, a speed change state, and / or an error state. Including
The updated set of waypoints is dynamically derived in response to the detection of the suspended state, the restarted state, the canceled state, the speed change state, and / or the error state, or their changes. At the same time, the adjustment for the task is dynamically performed.
The robot system according to claim 11. The at least one processor
Dynamically deriving the updated set of waypoints based on determining a target travel speed that is different from the planned travel speed associated with the planned set of waypoints.
Performing the adjustment for the task based on the transition from the current speed to the target movement speed across one or more waypoints in the updated set of waypoints.
11. The robot system according to claim 11. The at least one processor is based on determining a viable area along the planned trajectory and in front of the current position representing the target object and / or the representative portion of the robot. , Dynamically derive the updated set of waypoints,
11. The robotic system of claim 11, wherein the feasibility area is a position along the planned trajectory to represent a position where the adjustment for the task is first effective. A tangible, non-temporary computer-readable medium that stores processor instructions that cause one or more processors to perform a method when executed by one or more processors.
The method is
Receiving a planned trajectory for manipulating the target object,
Identifying a set of planned waypoints along the planned trajectory, each planned waypoint being said to place a representative portion of the target object or robot. Representing an increasingly targeted position on the orbit
Performing a task according to the planned trajectory by communicating a set of commands or settings for operating the robot so that the target object or the representative portion of the robot follows the planned trajectory. To get started and
Repetitively performing the task of transferring the target object or the representative portion of the robot to a subsequent planned waypoint on the planned orbit.
Monitoring input / output (I / O) states that represent the ability to complete the task execution and manipulation of the target object during the iterative execution of the segment movement.
Dynamically deriving an updated set of waypoints along the planned trajectory that replaces the planned set of waypoints based on the I / O state.
The said for transferring the target object or the representative portion of the robot according to the updated set of waypoints, rather than following the planned set of waypoints based on the I / O state. Performing adjustments to the task and
Tangible, non-temporary computer-readable media, including. Monitoring the I / O state represents a real-time real-world situation associated with the ability of the robot system to complete the task, a suspended state, a restart state, a canceled state, a speed change state, and / or an error. The state includes detecting during the execution of the task.
Dynamically deriving the updated set of waypoints and performing the adjustments to the task iteratively can be the suspended state, the restarted state, the canceled state, the speed change state, and /. Or, it is executed in response to the detection of the error state.
The tangible, non-temporary computer-readable medium of claim 17. Dynamically deriving the updated set of waypoints involves determining a target travel speed that is different from the planned travel speed associated with the planned set of waypoints.
Performing the adjustment for the task comprises transitioning to the target movement speed across one or more waypoints in the updated set of waypoints.
The tangible, non-temporary computer-readable medium of claim 17. Dynamically deriving the updated set of waypoints is an execution along the planned trajectory and in front of the current position representing the target object and / or the representative portion of the robot. Including determining the potential area
The feasibility area is intended to represent a position along the planned trajectory where the adjustment for the task is initially effective.
The tangible, non-temporary computer-readable medium of claim 17.

Images